I build AI systems that turn messy data into decisions.
Computer Science @ Notre Dame ’29 · Résumé · GitHub · LinkedIn · zjohnso4@nd.edu
Flagship projects
- Encore — Live-music app · Beta
A live-music app where an AI pipeline reads venue websites every day and decides which shows are reliable enough to publish. 221 venues · 2 cities: Atlanta and South Bend venues, pre-launch beta. - Vesper — Personal AI assistant · Daily use
An always-on AI assistant that knows my notes, deadlines and inbox, works from every device I own, and logs every action it takes. 23,744 events: logged by daily use since Sep 2, 2026. - OfferDesk — Internship tracker · Public repo
An internship tracker that tells you who to follow up with today — and that an AI assistant can update for you over MCP. 18 MCP tools: so an AI assistant can run the tracker for you. - alphalab — Strategy research lab · Building
A research lab that tests AI-written trading strategies honestly, so a lucky backtest can't pass as skill. 16 of 16 lucky strategies rejected: pre-registered, graded only on data they never saw. - Nudge study — Data analysis · Building
An analysis of 343 hand-judged nudges from my AI assistant that found repetition, not model confidence, separates useful from noise. 15% vs 58% useful: a rule's 11th+ firing vs. its 2nd–3rd, across 343 judged nudges.
Also built
- Shopwright — AI shop playbook · Public repo
An AI playbook for digital-download shops: it picks a niche from saved evidence, builds products as code, checks them, and waits for a human to approve. 37 checks: of automated QA on every product, plus an AI editor's rubric score. - E-ink note frame — Embedded gift build · Gift build
An ESP32 e-paper frame that shows notes sent over Telegram in a pixel-art speech bubble, with a live web mirror. ~1,470: lines of handwritten firmware, including a panel driver the library didn't have.